• 3 % discount on prepayment
  • Insured shipping from Switzerland
  • Sustainable: refurbished instead of new
  • Warranty on all cards
← Back to overview

Mistral-Small-4-119B-2603

Mistral AI
GermanApache 2.0

Open language model for chat and text. 3 sizes from 119.4B to 675B parameters, partly mixture-of-experts (only a part of the parameters is active per token).

  • Mixture-of-experts: 119.4B parameters in total, of which 7.1B active per token. Memory requirement depends on all parameters, speed on the active ones.

Settings

Quality
4 bit (Q4_K_M) is the most common choice: good quality with low memory requirements.
Context length: 8k tokens
4k256k
How much text the model keeps in view at once. More context needs more memory.
Recommendation
1× H100 80 GB

The model needs about 73.3 GB of memory. Hopper, FP8 support.

Weights
71.6 GB
KV cache
0.2 GB
Speed
~234.9 Tok./s

More suitable configurations

CardQuantityTok./sStatus
Tesla T4 16 GB8×26.12-3 weeks delivery time
Tesla P100 16 GB8×32.82-3 weeks delivery time
Tesla P40 24 GB4×38.72-3 weeks delivery time
Tesla V100 16 GB8×72.6only 1 in stock
Tesla V100 32 GB4×91.3On order, delivery time approx. 1 week
AMD Instinct MI50 16 GB8×55.6only 2 in stock
AMD Instinct MI50 32 GB4×70.0only 2 in stock
AMD Instinct MI60 32 GB4×64.62-3 weeks delivery time
AMD Instinct MI100 32 GB4×78.22-3 weeks delivery time
A30 24 GB4×88.32-3 weeks delivery time
RTX A5000 24 GB4×92.02-3 weeks delivery time
A40 48 GB2×100.82-3 weeks delivery time